Abstract: Many great research ideas and new languages are emerging for programmable forwarding. In this talk, I'll take a step back and consider how we got here, why programmable forwarding planes are inevitable, why now is the right time, why they are a final frontier for SDN, and why they are here to stay.

Bio: Nick McKeown (PhD/MS UC Berkeley ’95/’92; B.E Univ. of Leeds, ’86) is the Kleiner Perkins, Mayfield and Sequoia Professor of Electrical Engineering and Computer Science at Stanford University, and Faculty Director of the Open Networking Research Center. From 1986-1989 he worked for Hewlett-Packard Labs in Bristol, England. In 1995, he helped architect Cisco's GSR 12000 router. Nick was co-founder and CTO at Abrizio (acquired by PMC-Sierra, 1998), co-founder and CEO of Nemo (“Network Memory”),acquired by Cisco, 2005. In 2007 he co-founded Nicira (acquired by VMware) with Martin Casado and Scott Shenker. Nick is chairman of Barefoot Networks which he co-founded with Pat Bosshart and Martin Izzard in 2013. In 2011, he co-founded the Open Networking Foundation (ONF) with Scott Shenker; and the Open Networking Lab (ON.Lab) with Guru Parulkar and Scott Shenker. Nick is a member of the US National Academy of Engineering (NAE), the American Academy of Arts and Sciences, a Fellow of the Royal Academy of Engineering (UK), the IEEE and the ACM. He received the British Computer Society Lovelace Medal (2005), the IEEE Kobayashi Computer and Communications Award (2009), the ACM Sigcomm Lifetime Achievement Award (2012), the IEEE Rice communications theory award (1999). Nick has an Honorary Doctorate from ETH (Zurich, 2014). Nick's current research interests include software defined networks (SDN), network verification, video streaming, how to enable more rapid improvements to the Internet infrastructure, and tools and platforms for networking research and teaching.

Abstract: Large networks rely on timely and accurate measurements to detect unwanted traffic, diagnose performance problems, and optimize the use of resources. Emerging programmable forwarding planes are a "game changer" for answering sophisticated measurement questions directly inside the network, rather than shipping reams of data to a remote collector for subsequent analysis. Capitalizing on these new switch capabilities requires innovation in rich, high-level query abstractions as well as runtime systems that can generate efficient data structures for streaming analytics at line rate.

Bio: Jennifer Rexford (PhD/MSE UMichigan '96/'93, BSE Princeton '91) is the Gordon Y.S. Wu Professor of Engineering and the Chair of Computer Science at Princeton University. Before joining Princeton in 2005, she worked for eight years at AT&T Labs–Research. Jennifer is co-author of the book "Web Protocols and Practice" (Addison-Wesley, May 2001). She served as the chair of ACM SIGCOMM from 2003 to 2007, and a member of the Open Networking Foundation board of directors from 2014 to 2017. Jennifer received ACM's Grace Murray Hopper Award (2004) and Athena Lecturer Award (2016). She is an ACM Fellow (2008), and a member of the American Academy of Arts and Sciences (2013) and the National Academy of Engineering (2014).

Abstract: NetEgg is a scenario-based programming toolkit that allows network operators to program network policies by describing representative example behaviors. Given these scenarios, a synthesis algorithm automatically infers the controller state that needs to be maintained along with the rules to process network events and update state. NetEgg executes the generated policy implementation on top of a centralized controller, and automatically infers flow-table rules that can be pushed to switches to improve throughput. This talk will present the design and implementation of the NetEgg toolkit, empirical results on multiple example policies, and experiences on running controlled user studies. The talk concludes with a discussion on the importance of controlled user studies in evaluating new programming languages in the networking domain and the lessons we learnt in the process.

Bio: Boon Thau Loo is an Associate Professor in the Computer and Information Science (CIS) department at the University of Pennsylvania. He holds a secondary appointment in the Electrical and Systems Engineering (ESE) department. He is also the CIS Masters Chair, overseeing all masters programs within the CIS department, and Director of the Master of Science in Engineering in CIS program. He received his Ph.D. degree in Computer Science from the University of California at Berkeley in 2006. Prior to his Ph.D, he received his M.S. degree from Stanford University in 2000, and his B.S. degree with highest honors from UC Berkeley in 1999. His research focuses on distributed data management systems, Internet-scale query processing, and the application of data-centric techniques and formal methods to the design, analysis and implementation of networked systems. He was awarded the 2006 David J. Sakrison Memorial Prize for the most outstanding dissertation research in the Department of EECS at UC Berkeley, and the 2007 ACM SIGMOD Dissertation Award. He is a recipient of the NSF CAREER award (2009) and the Air Force Office of Scientific Research (AFOSR) Young Investigator Award (2012). He has published 100+ peer reviewed publications and has supervised twelve Ph.D dissertations. His graduated Ph.D. students include 3 tenure-track faculty members and winners of 3 dissertation awards. He is also co-founder and Chief Scientist at Termaxia, a big data storage startup.

Abstract:

Modern networks store states at individual nodes. This allows the forwarding behavior to change over time, which is useful to implement many kinds of functionalities for performance and security. However, this makes the task of network programming hard and error-prone. I will describe several abstractions that simplify the task of proving the safety of stateful networks. The abstraction include modelling state changes as a finite-state machine, ignoring the order of packet receival, and assuming that nodes can non-deterministically reset to their initial states. I will show that these abstractions reduce the asymptotic complexity of network verification.

This is a joint work with Kalev Alpernas (TAU), Aurojt Panda (UCB), Roman Manevich (BGU), Scott Shenker (UCB), Sharon Shoham (TAU), Yaron Velner (HUJI)

Bio: Mooly serves as Member of the Advisory Board at Panaya Inc. He is a Senior Member of staff in the Computer Sciences Department School of Mathematical Sciences Tel-Aviv University. A leading scientist in large scale (inter-procedural) program analysis, his fields of interests include Programming Languages, Compilers, Abstract interpretation, Profiling, Pointer Analysis, Shape Analysis, Inter-procedural dataflow analysis, Program Slicing, Language-based programming environments.

Abstract:

Enterprise networks have become complex software artifacts weaving together interdependent devices, protocols, virtualization layers, optimizations, software bugs, and security controls. Yet communication is now critical infrastructure. How can we be sure networks are doing the right thing? The fact is, too often, they aren't. Despite enormous amounts of manual effort, outages and security vulnerabilities are common.

Can we prove that a network is correct? This is the goal of the emerging area of network verification, which applies ideas of formal methods to network infrastructure. From its recent genesis in the research community, network verification blossomed into a hot area of research and quickly had impact on industry, with startups and hyperscale cloud providers deploying verification technology today. In this talk, we'll briefly review key research advances that influenced industrial verification software. Then, based on experience with production deployments, we will discuss what principles of verification persevered, what surprises we encountered, and how verification is solving problems in the real world. Finally, we will discuss challenging future research directions.

Bio: Wenxuan Zhou is a software engineer at Veriflow and a Ph.D. student in Computer Science at the University of Illinois at Urbana-Champaign (UIUC), advised by Prof. Matthew Caesar. Her research focuses on network verification and synthesis, with an emphasis on software-defined networks, data centers, and enterprise networks. She received her Bachelor’s degree in Electronic Engineering from Beijing University of Aeronautics and Astronautics, China, and her Master’s degree in Computer Science from UIUC. She co-authored research that led to network verification startup Veriflow, where she serves as one of the original engineers on the core verification team.